Related papers: Can You Trust the Vectors in Your Vector Database?…
The software build process transforms source code into deployable artifacts, representing a critical yet vulnerable stage in software development. Build infrastructure security poses unique challenges: the complexity of multi-component…
As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm. In this paper, we investigate the interplay between vulnerabilities of the image scaling…
Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as images. In this work, we propose a novel backdoor attack on…
Not long ago, it was thought that only software applications and general purpose digital systems i.e. computers were prone to various types of attacks against their security. The underlying hardware, hardware implementations of these…
The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…
While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and…
Vectors are universal mathematical objects that can represent text, images, speech, or a mix of these data modalities. That happens regardless of whether data is represented by hand-crafted features or learnt embeddings. Collect a large…
In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to…
We apply distributed language embedding methods from Natural Language Processing to assign a vector to each database entity associated token (for example, a token may be a word occurring in a table row, or the name of a column). These…
Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…
Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. However, it was also discovered that DNNs are vulnerable to multiple kinds of attacks, including Backdoor Attacks. Through the attack, the attacker…
Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…
Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease…
We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…
Vector databases have become a cornerstone of modern information retrieval, powering applications in recommendation, search, and retrieval-augmented generation (RAG) pipelines. However, scaling approximate nearest neighbor (ANN) search to…
Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
A classical vector retrieval problem typically considers a \emph{single} query embedding vector as input and retrieves the most similar embedding vectors from a vector database. However, complex reasoning and retrieval tasks frequently…
Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of queries to the model and then leveraging the model's predictions…